Displaying 1 to 2 from 2 results

FTRL - R/Rcpp implementation of the 'Follow-the-Regularized-Leader' algorithm

  •    R

R package which implements Follow the proximally-regularized leader algorithm. It allows to solve very large problems with stochastic gradient descend online learning. See Ad Click Prediction: a View from the Trenches for example.

rsparse - Fast and accurate machine learning on sparse matrices - Factorization Machines, FTRL, Matrix factorizations

  •    R

rsparse is an R package for statistical learning on sparse data. Notably it implements many algorithms sparse matrix factorizations with a focus on applications for recommender systems. All of the algorithms benefit from OpenMP and most of them use BLAS. Package scales nicely to datasets with millions of rows and millions of columns.